Abstract
We report in this paper some positive simulation results obtained when image pixels are directly used as input state of a reinforcement learning algorithm. The reinforcement learning algorithm chosen to carry out the simulation is a batch-mode algorithm known as fitted Q iteration.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research 6, 503–556 (2005)
Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Machine Learning 36(1), 3–42 (2006)
Jodogne, S., Piater, S.: Interactive learning of mappings from visual percepts to actions. In: De Raedt, L., Wrobel, S. (eds.) Proceedings of the 22nd International Conference on Machine Learning, pp. 393–400 (August 2005)
Lagoudakis, M., Parr, R.: Reinforcement learning as classification: leveraging modern classifiers. In: Faucett, T., Mishra, N. (eds.) Proceedings of 20th International Conference on Machine Learning, pp. 424–431 (2003)
Marée, R., Geurts, P., Piater, J., Wehenkel, L.: Random subwindows for robust image classification. In: Schmid, C., Soatto, S., Tomasi, C. (eds.) Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 34–40. IEEE, Los Alamitos (June 2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ernst, D., Marée, R., Wehenkel, L. (2006). Reinforcement Learning with Raw Image Pixels as Input State. In: Zheng, N., Jiang, X., Lan, X. (eds) Advances in Machine Vision, Image Processing, and Pattern Analysis. IWICPAS 2006. Lecture Notes in Computer Science, vol 4153. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11821045_47
Download citation
DOI: https://doi.org/10.1007/11821045_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-37597-5
Online ISBN: 978-3-540-37598-2
eBook Packages: Computer ScienceComputer Science (R0)